
Hosted by David Vuong and Ilan Rotenberg · EN

Set up a decentralized agent team in OpenClaw to complete complex tasks. We walk you through a real use case to set up a morning briefing using two agents, a researcher and a summarizer. They hand off work to each other on a schedule so you wake up to a one-minute AI news brief on your phone. Chapters 00:00 - Intro00:47 - Why You Need an Agent Team02:50 - Agent Team Patterns04:50 - Ilan's Morning Briefing Setup08:30 - How Zoe Was Built10:50 - Wrap-Up and Key Takeaways Business Use Cases - Set up a decentralized agent team in OpenClaw where each agent saves its output to a workspace file and the next agent picks it up to complete its part of the task.- Use cron jobs to schedule agents in sequence with time gaps between them, then test each agent manually before automating.- Give each agent a pop culture persona that matches the work style you want, and define a clear output contract (a saved file) so the agent knows exactly when its job is done. Links OpenClaw - https://openclaw.aiOpenClaw GitHub - https://github.com/openclaw/openclawOpenClaw Docs - https://docs.openclaw.aiAgent Team Builder Skill - https://github.com/canuckamok/agents/tree/main/skills Find Us YouTube - https://www.youtube.com/@PandCpodcastBluesky - https://bsky.app/profile/pandcpodcast.bsky.socialX - https://x.com/_pandcpodcastInstagram - https://www.instagram.com/_pandcpodcastLinkedIn - https://www.linkedin.com/company/p-and-c-podcast (00:00) - Intro (01:06) - Why You Need an Agent Team (02:52) - Agent Team Patterns (04:43) - Ilan's Morning Briefing Setup (08:26) - How Zoe Was Built (11:15) - Wrap-Up & Key Takeaways

In this episode of Prompt and Circumstance, we explore Stitch by Google, a free tool that is democratizing high-end web and app design. Whether you are a small business owner tired of mediocre layouts or an entrepreneur looking to prototype at lightning speed, Stitch allows you to generate professional design systems and deployable code using simple conversational prompts.WHAT YOU'LL LEARNINSTANT DESIGN SYSTEMS: See how the AI generates full palettes, typography, and background imagery automatically.THE "AGENCY KILLER": Why you no longer need to pay thousands of dollars for initial ideation and palette iterations.DESIGN "INSPIRATION": With some screenshots, you can get the AI to mimic the style of your favorite existing websites.VIDEOClick here to watch a video of this episode. TIMESTAMPS00:00 - Intro01:07 - Fire your web design agency04:03 - Get "inspired" by another websiteLINKSStitch - https://stitch.withgoogle.com/Merch - https://devilwearsproduct.shop/

If you want an AI agent that handles your repetitive tasks while you sleep, watch this.We got tired of clicking the same buttons and reading 50 newsletters a day just to keep up with tech. It takes way too much time. So we stopped doing it manually. Now, we have an autonomous agent that wakes up early, scrapes the internet, and writes a 30-second brief for us.In this episode of Prompt and Circumstance, we show you exactly how we built this using OpenClaw. OpenClaw isn't just another text box. It actually takes over your mouse and keyboard. It opens applications and executes tasks exactly like a human would.Here is what we cover:What OpenClaw actually is and why it beats standard chatbotsHow to skip the complicated terminal commands and install it on HostingerHow to configure the system messages so your agent knows exactly how to behaveThe exact setup we use to make it valuable for our own daily workVIDEO LINKClick here to watch a video of this episode. SECTIONS00:00 - Intro00:46 - What is OpenClaw07:43 - How to set up OpenClaw11:36 - Walkthrough of useful setup24:11 - ConclusionsLINKSMerch - https://www.devilwearsproduct.shop/Hostinger - https://www.hostinger.com/ca?REFERRALCODE=9SGMILANUEYM Openclaw Git Repo - https://github.com/openclaw/openclawPeter Steinberger - https://en.wikipedia.org/wiki/Peter_Steinberger_(programmer)Setting up your OpenAI account with OpenClaw - https://lumadock.com/tutorials/openclaw-openai-codex-chatgpt-subscription Openrouter - https://openrouter.ai/

In this episode: how to generate 30+ second synchronized videos using free, open-source tools. No subscriptions, no cloud. David walks through the ComfyUI workflow for image-to-video generation. He covers image preparation with Qwen 2.5, video rendering with Infinite Talk and WAN 2.1, and configuring resolution, frame count, and prompts. Includes a live demo and an honest look at lip sync limitations. CHAPTERS 00:00 — Introduction 01:48 — Base Image Generation With ComfyUI 05:39 — Generate Long Videos With Infinite Talk 11:56 — Settings and Prompt Writing 14:43 — Demo and Limitations SPONSORS Querio → querio.ai Devil Wears Product (Merch Store) - https://devilwearsproduct.shop LINKS ComfyUI - https://www.comfy.org/ Qwen Image Edit - https://docs.comfy.org/tutorials/image/qwen/qwen-image-edit-2511 Infinite Talk - https://infinitetalk.org/ Infinite Talk Repo - https://meigen-ai.github.io/InfiniteTalk/ Infinite Talk Workflow - https://pastebin.com/PYBBXTY6 (password: PromptandCircumstance) wav2vec2 - https://huggingface.co/facebook/wav2vec2-base FIND US YouTube - https://www.youtube.com/@PandCpodcast Bluesky - https://bsky.app/profile/pandcpodcast.bsky.social X - https://x.com/_pandcpodcast Instagram - https://www.instagram.com/_pandcpodcast LinkedIn - https://www.linkedin.com/company/p-and-c-podcast

We teach you how we are generating music and speech entirely on a local machine using open source models in ComfyUI, no cloud subscriptions to ElevenLabs or Suno required. You'll see how ACE-Step 1.5 produces full pop songs from a text prompt and how Qwen3-TTS clones voices from a short audio clip, all on consumer-grade hardware.Chapters00:00 - Intro and What We're Covering00:56 - Making Music Locally with ACE-Step 1.502:47 - Setting Up the Workflow in ComfyUI04:40 - Prompting for Songs: Descriptions, Lyrics, and Settings10:22 - Generating an Instrumental EDM Track with Gemini12:43 - Local Speech Generation and Voice Cloning with Qwen3-TTS18:18 - Deepfake Concerns and Wrap UpSponsorsQuerio → querio.aiDevil Wears Product (Merch Store) - https://devilwearsproduct.shopLinksACE-Step 1.5 (GitHub) - https://github.com/ace-step/ACE-Step-1.5ACE-Step 1.5 (Hugging Face) - https://huggingface.co/ACE-Step/Ace-Step1.5Qwen3-TTS (GitHub) - https://github.com/QwenLM/Qwen3-TTSComfyUI-Qwen-TTS (ComfyUI Nodes) - https://github.com/flybirdxx/ComfyUI-Qwen-TTSComfyUI - https://www.comfy.org/ElevenLabs - https://elevenlabs.ioSuno - https://suno.comGoogle Gemini - https://gemini.google.comFind UsYouTube - https://www.youtube.com/@PandCpodcastBluesky - https://bsky.app/profile/pandcpodcast.bsky.socialX - https://x.com/_pandcpodcastInstagram - https://www.instagram.com/_pandcpodcastLinkedIn - https://www.linkedin.com/company/p-and-c-podcast

Build your own RAG (Retrieval Augmented Generation) agent in 25 minutes. If you're building AI products, or you want to be, you've heard the term thrown around. We believe in learning by doing, so on this episode we teach you how to build your own RAG agent from scratch. You'll learn key terminology like vector store and embedding, and you'll have a working agent by the end. Walk away with the confidence to talk about RAG with your business and technical stakeholders.The workflow examples from this episode are available for download on Github here. Simply open a new workflow, click the import from URL button, and paste the link from Github.A step-by-step guide can be found here.Chapters00:00 - What Is RAG and Why Product Teams Should Care04:10 - Tools and Prerequisites for the Build07:07 - Building the Data Ingestion Workflow in N8N13:11 - Connecting Embeddings and Document Loaders17:20 - Building the Chat Agent21:50 - Testing the RAG Agent LiveKey TopicsRAG (Retrieval Augmented Generation): How RAG lets an LLM search over specific documents instead of pulling from its entire training dataVector Databases: What they are, how they store information for LLM retrieval, and why Supabase works well for thisEmbeddings Models: How Cohere's embedding model translates text into a format LLMs use for similarity searchN8N Workflow Setup: Step-by-step walkthrough of building both the data ingestion and chat agent workflowsDimension Matching: Why your embeddings model and database table must use the same number of dimensions or your results will be uselessThe Think Tool: How a scratchpad tool helps AI agents remember why they made decisions during multi-step processesMetadata in Vector Stores: Adding properties like author, likes, and retweets to give the LLM more context about stored documentsSponsorsQuerio → querio.ain8n → https://n8n.partnerlinks.io/9tsc8o37mvs2Linksn8n Workflow for Download - https://github.com/canuckamok/agents/tree/main/tweet-ragSupabase - https://supabase.comCohere - https://cohere.com8N - https://n8n.ioX Developer Console - https://console.x.comGoogle NotebookLM - https://notebooklm.googleQuerio - https://querio.aiFind UsYouTube - https://www.youtube.com/@PandCpodcastBluesky - https://bsky.app/profile/pandcpodcast.bsky.socialX - https://x.com/_pandcpodcastInstagram - https://www.instagram.com/_pandcpodcastLinkedIn - https://www.linkedin.com/company/p-and-c-podcast

David shows you how to generate and edit AI images completely free on your own machine using open source models and ComfyUI. This means you can generate AI images without any watermark, no privacy concerns, and no additional API costs. Watch as David takes you through how these models work and shows the amazing results that were good enough to be used in our web store.CHAPTERS00:00 - Welcome and Episode Overview01:18 - Why Local Image Generation Matters02:25 - Getting Started with ComfyUI05:40 - Comparing Qwen Image vs Z Image Turbo12:46 - Image Editing with Flux 2 Klein16:28 - Creating Stock Photos for Your Brand17:54 - Advantages of Local GenerationSPONSORSQuerion8nDevil Wears Product (Merch Store) - https://devilwearsproduct.shop [RELAUNCHING SOON]LINKSComfyUI - https://www.comfy.orgBlack Forest Labs (Flux) - https://bfl.aiQwen-Image-2512 model page - https://huggingface.co/Qwen/Qwen-Image-2512Z-Image-Turbo model page - https://huggingface.co/Tongyi-MAI/Z-Image-TurboFIND USYouTube - https://www.youtube.com/@PandCpodcastBluesky - https://bsky.app/profile/pandcpodcast.bsky.socialX - https://x.com/_pandcpodcastInstagram - https://www.instagram.com/_pandcpodcastLinkedIn - https://www.linkedin.com/company/p-and-c-podcast

Wondering how to take your proof of concept agent to production? Ilan walks through three key lessons from building a competitive analysis agent in n8n, including tips for optimizing your prompts, how to break work into sub-agents, analyze logs, and rethink your workflow design.CHAPTERS00:00 - Intro and Episode Overview01:31 - Sponsor: Querio01:59 - The Competitive Analysis Agent Problem04:29 - Lesson 1: Use Observability and Logs to Debug06:43 - Hitting Token Limits and Iteration Caps09:05 - Lesson 2: Split Into Sub-Agents When Needed12:40 - The Parallel Processing Problem in n8n14:11 - Lesson 3: Sequential Design When Tools Don't Run Parallel16:29 - Wrapping Up and Key TakeawaysKEY LESSONSLesson 1: Use observability and logs to debug agent performance. When the market research agent missed a $100M Series C raise, analyzing n8n logs revealed superficial Perplexity requests, leading to prompt optimization techniques like specifying exact information types (official news, product updates, partnerships, industry coverage) instead of letting the agent decide what to search for.Lesson 2: Split into sub-agents when hitting limits or performance issues. Token limits (10,000 per second on Anthropic) and iteration caps (10 default in n8n) mean one agent doing too many jobs leads to context growth and hallucination risk. Breaking into focused sub-agents (news researcher, sentiment analysis) with specific prompts solves this.Lesson 3: Design for sequential execution when tools don't support parallel processing. n8n runs left to right, top to bottom, so forcing a parallel-looking workflow creates unpredictable execution order. Accepting sequential design and removing deterministic steps (like pulling competitor lists from Google Sheets) from agent control improves reliability.SPONSORSQuerio → querio.ain8n → n8n.ioLINKSDownload the n8n workflow here n8n - https://n8n.ioPerplexity - https://www.perplexity.aiProduct Compass (Pawel Huryn) AI Agent WorkshopFIND USYouTube - https://www.youtube.com/@PandCpodcastBluesky - https://bsky.app/profile/pandcpodcast.bsky.socialX - https://x.com/_pandcpodcastInstagram - https://www.instagram.com/_pandcpodcastLinkedIn - https://www.linkedin.com/company/p-and-c-podcast

Andrew Williams, CEO of the Toronto Product Management Association, shares his approach to AI-powered product building. He focuses on his app Heyday Focus that makes it easy to follow best practices for increasing focus while online. He discusses how he started his journey in Lovable, then switched to Claude Code and Cursor. He also dives deep into how to use AI tools to create tasteful designs for consistent, polished development.Chapters 00:00 - Andrew's Background: From Publishing to Music to Product 03:52 - The Focus Problem and Introducing Heyday 09:18 - Vibe Coding Journey: From Lovable to Cursor 12:18 - Heyday Demo: Chrome Extension Walkthrough 16:39 - Feature Scoping and the Shadow App Concept 20:46 - Live Demo: Using Figma Make to Redesign Heyday in an Afternoon 24:14 - Next Steps and Where to Find AndrewGuestAndrew Williams - CEO, Toronto Product Management Association & Founder, HeydayLinkedIn: linkedin.com/in/andrewrwilliams X: https://x.com/andrew_reset Substack: andrew_reset.substack.comSponsors N8N → n8n.io Querio → querio.aiLinks Heyday - https://heydayfocus.com Toronto Product Management Association - https://tpma.ca Figma Make - https://figma.com/make v0 by Vercel - https://v0.dev Cursor - https://cursor.com Claude - https://claude.ai Lovable - https://lovable.dev Find Us YouTube - https://www.youtube.com/@PandCpodcast Bluesky - https://bsky.app/profile/pandcpodcast.bsky.social X - https://x.com/_pandcpodcast Instagram - https://www.instagram.com/_pandcpodcast LinkedIn - https://www.linkedin.com/company/p-and-c-podcastNote: Andrew will be sharing his Claude Skills files and design philosophy templates - we'll add those links once available!

We interview Hira Siddiqui, the technical founder who hit #1 on Product Hunt with AI Context Flow while working full-time. She breaks down how she got okay asking for money, built a productivity tool with a mission, and why the difference between context and memory might be the most important thing you're not thinking about.CHAPTERS00:00 - Introduction and Guest Welcome01:47 - Hira's Background: From R&D to Solutions Architect03:40 - The Origin Story: Self-Sovereign Identity and Data Silos13:29 - The 10x Pivot: When AI Agents Changed Everything26:43 - Context vs Memory: What Most People Get Wrong31:41 - Where to Find Hira and ClosingGUESTHira Siddiqui - Founder of Plurality Network | LinkedIn: https://www.linkedin.com/in/hirasiddiqui247/SPONSORSQuerio → querio.ain8n → n8n.io LINKSAI Context FlowProduct HuntPlurality NetworkHira's Medium Blog on Zero-Knowledge ProofsFIND USYouTube - https://www.youtube.com/@PandCpodcastBluesky - https://bsky.app/profile/pandcpodcast.bsky.socialX - https://x.com/_pandcpodcastInstagram - https://www.instagram.com/_pandcpodcastLinkedIn - https://www.linkedin.com/company/p-and-c-podcast